Remove unsafe file.unlink() calls that delete data before download

swvo/io/dst/wdc.py

@@ -88,11 +88,8 @@ def download_and_process(self, start_time: datetime, end_time: datetime, reproce
 
                 URL = self.URL.replace("YYYYMM", time_interval.strftime("%Y%m"))
 
-                if file_path.exists():
-                    if reprocess_files:
-                        file_path.unlink()
-                    else:
-                        continue
+                if file_path.exists() and not reprocess_files:
+                    continue
 
                 logging.debug(f"Downloading file {URL + filename} ...")
 
@@ -192,8 +189,6 @@ def _process_single_file(self, file_path: Path, year, month) -> pd.DataFrame:
         df.index = df["timestamp"]
         df.drop(columns=["timestamp"], inplace=True)
 
-        file_path.unlink()
-
         return df
 
     def read(self, start_time: datetime, end_time: datetime, download: bool = False) -> pd.DataFrame:

swvo/io/hp/gfz.py

@@ -103,19 +103,16 @@ def download_and_process(
                         f"Hp{self.index_number}/Hp{self.index_number}_ap{self.index_number}_nowcast.txt"
                     )
 
+                if file_path.exists() and not reprocess_files:
+                    continue
+
                 for filename_download in filenames_download:
                     logging.debug(f"Downloading file {self.URL + filename_download} ...")
 
                     wget.download(self.URL + filename_download, str(temporary_dir))
 
                     logging.debug("Processing file ...")
 
-                    if file_path.exists():
-                        if reprocess_files:
-                            file_path.unlink()
-                        else:
-                            continue
-
                 filenames_download = [x[5:] for x in filenames_download]  # strip of folder of filename
 
                 processed_df = self._process_single_file(temporary_dir, filenames_download)

swvo/io/kp/niemegk.py

@@ -99,11 +99,8 @@ def download_and_process(self, start_time: datetime, end_time: datetime, reproce
             file_paths, time_intervals = self._get_processed_file_list(start_time, end_time)
 
             for file_path, time_interval in zip(file_paths, time_intervals):
-                if file_path.exists():
-                    if reprocess_files:
-                        file_path.unlink()
-                    else:
-                        continue
+                if file_path.exists() and not reprocess_files:
+                    continue
 
                 data_single_file = processed_df[
                     (processed_df.index >= time_interval[0]) & (processed_df.index <= time_interval[1])

swvo/io/kp/swpc.py

@@ -83,11 +83,8 @@ def download_and_process(self, target_date: datetime, reprocess_files: bool = Fa
 
         file_path = self.data_dir / f"SWPC_KP_FORECAST_{target_date.strftime('%Y%m%d')}.csv"
 
-        if file_path.exists():
-            if reprocess_files:
-                file_path.unlink()
-            else:
-                return
+        if file_path.exists() and not reprocess_files:
+            return
 
         temporary_dir = Path("./temp_kp_swpc_wget")
         temporary_dir.mkdir(exist_ok=True, parents=True)

swvo/io/omni/omni_high_res.py

@@ -98,11 +98,8 @@ def download_and_process(
             file_paths, time_intervals = self._get_processed_file_list(start_time, end_time, cadence_min)
 
             for file_path, time_interval in zip(file_paths, time_intervals):
-                if file_path.exists():
-                    if reprocess_files:
-                        file_path.unlink()
-                    else:
-                        continue
+                if file_path.exists() and not reprocess_files:
+                    continue
 
                 data = self._get_data_from_omni(
                     start=time_interval[0],

swvo/io/omni/omni_low_res.py

@@ -141,11 +141,8 @@ def download_and_process(self, start_time: datetime, end_time: datetime, reproce
             for file_path, time_interval in zip(file_paths, time_intervals):
                 filename = "omni2_" + str(time_interval[0].year) + ".dat"
 
-                if file_path.exists():
-                    if reprocess_files:
-                        file_path.unlink()
-                    else:
-                        continue
+                if file_path.exists() and not reprocess_files:
+                    continue
 
                 logging.debug(f"Downloading file {self.URL + filename} ...")